Abstract
This chapter discusses the use of regression forests for the automatic detection and simultaneous localization of multiple anatomical regions within computed tomography (CT) and magnetic resonance (MR) three-dimensional images. Important applications include: organ-specific tracking of radiation dose over time; selective retrieval of patient images from radiological database systems; semantic visual navigation; and the initialization of organ-specific image processing operations. We present a continuous parametrization of the anatomy localization problem, which allows it to be addressed effectively by multivariate random regression forests (Chap. 5). A single pass of our probabilistic algorithm enables the direct mapping from voxels to organ location and size, with training focusing on maximizing the confidence of output predictions. As a by-product, our method produces salient anatomical landmarks, i.e. automatically selected “anchor” regions which help localize organs of interest with high confidence. This chapter builds upon the work in Criminisi et al., in MICCAI workshop on medical computer vision: recognition techniques and applications in medical imaging, 2010 and in Pauly et al., Proc medical image computing and computer assisted intervention, 2011 and demonstrates the flexibility of forests in dealing with both CT and multi-channel MR scans. Quantitative validation is performed on two ground truth labeled datasets: (i) a database of 400 highly variable CT scans, and (ii) a database of 33 full-body, multi-channel MR scans. In both cases localization errors are reduced and results are more stable than those from more conventional atlas-based registration approaches. The simplicity of the regressor’s context-rich visual features yield typical run-times of only 4 seconds per scan on a standard desktop. This anatomy recognition algorithm has now received FDA approval and is part of Caradigm’s Amalga (www.caradigm.com).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
DICOM tags for the anatomical region are often erroneous [147].
- 2.
As opposed to classification where the predicted variables are categorical.
- 3.
Superscripts follow standard radiological orientation convention: L=left, R=right, A=anterior, P=posterior, H=head, F=foot.
- 4.
This metric is appropriate in light of our intended data retrieval and semantic navigation applications because the bounding box centroid would typically be used to select which coronal, axial, and sagittal slices to display to the user. If the ground truth bounding box contains the centroid of the predicted bounding box, then the selected slices will intersect the organ of interest.
References
Criminisi A, Shotton J, Bucciarelli S (2009) Decision forests with long-range spatial context for organ localization in CT volumes. In: MICCAI workshop on probabilistic models for medical image analysis (PMMIA)
Criminisi A, Shotton J, Robertson D, Konukoglu E (2010) Regression forests for efficient anatomy detection and localization in CT studies. In: MICCAI workshop on medical computer vision: recognition techniques and applications in medical imaging, Beijing. Springer, Berlin
Criminisi A, Shotton J, Konukoglu E (2012) Decision forests: a unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Found Trends Comput Graph Vis 7(2–3)
Fenchel M, Thesen S, Schilling A (2008) Automatic labeling of anatomical structures in MR FastView images using a statistical atlas. In: Proc medical image computing and computer assisted intervention (MICCAI)
Feulner J, Zhou SK, Seifert S, Cavallaro A, Hornegger J, Comaniciu D (2009) Estimating the body portion of CT volumes by matching histograms of visual words. In: Pluim JPW, Dawant BM (eds) Proc Intl society for optical engineering (SPIE) medical imaging
Friedman J (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 2(28)
Gall J, Lempitsky V (2009) Class-specific Hough forests for object detection. IEEE Trans Pattern Anal Mach Intell
Glocker B, Feulner J, Criminisi A, Haynor DR, Konukoglu E (2012) Automatic localization and identification of vertebrae in arbitrary field-of-view CT scans. In: Proc medical image computing and computer assisted intervention (MICCAI)
Gueld MO, Kohnen M, Keysers D, Schubert H, Wein BB, Bredno J, Lehmann TM (2002) Quality of DICOM header information for image categorization. In: SPIE storage and retrieval for image and video databases, San Diego
Hardle W (1990) Applied non-parametric regression. Cambridge University Press, Cambridge
Isgum I, Staring M, Rutten A, Prokop M, Viergever MA, van Ginneken B (2009) Multi-atlas-based segmentation with local decision fusion: application to cardiac and aortic segmentation in CT scans. Trans Med Imaging 28(7)
Klein S, Staring M, Murphy K, Viergever MA, Pluim JP (2010) Elastix: a toolbox for intensity-based medical image registration. Trans Med Imaging 29
Konukoglu E, Criminisi A, Pathak S, Robertson D, White S, Haynor D, Siddiqui K (2011) Robust linear registration of CT images using random regression forests. In: Proc intl society for optical engineering (SPIE) medical imaging
Ma J (2008) Dixon techniques for water and fat imaging. J Magn Reson Imaging
Nelder JA, Mead R (1965) A simplex method for function minimization. Comput J 7(4)
Ojala T, Pietikainen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recognit 29
Pathak S, Criminisi A, White S, Munasinghe I, Sparks B, Robertson D, Siddiqui K (2011) Automatic semantic annotation and validation of anatomy in DICOM CT images. In: Proc intl society for optical engineering (SPIE) medical imaging
Pauly O, Glocker B, Criminisi A, Mateus D, Martinez Möller A, Nekolla S, Navab N (2011) Fast multiple organs detection and localization in whole-body MR Dixon sequences. In: Proc medical image computing and computer assisted intervention (MICCAI), Toronto
Seifert S, Barbu A, Zhou SK, Liu D, Feulner J, Huber M, Sühling M, Cavallaro A, Comaniciu D (2009) Hierarchical parsing and semantic navigation of full body CT data. In: Pluim JPW, Dawant BM (eds) Proc intl society for optical engineering (SPIE) medical imaging
Shimizu A, Ohno R, Ikegami T, Kobatake H (2006) Multi-organ segmentation in three-dimensional abdominal CT images. Int J Comput Assisted Radiol Surg 1
Shotton J, Winn JM, Rother C, Criminisi A (2009) TextonBoost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. Int J Comput Vis 81(1)
Torralba A, Murphy KP, Freeman WT (2007) Sharing visual features for multiclass and multiview object detection. IEEE Trans Pattern Anal Mach Intell 19(5)
Vapnik V (2000) The nature of statistical learning theory. Springer, Berlin
Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vis 57(2)
Yao C, Wada T, Shimizu A, Kobatake H, Nawano S (2006) Simultaneous location detection of multi-organ by atlas-guided eigen-organ method in volumetric medical images. Int J Comput Assisted Radiol Surg 1
Yin P, Criminisi A, Winn J, Essa I (2007) Tree based classifiers for bilayer video segmentation. In: Proc IEEE conf computer vision and pattern recognition (CVPR)
Zhan Y, Zhou X-S, Peng Z, Krishnan A (2008) Active scheduling of organ detection and segmentation in whole-body medical images. In: Proc medical image computing and computer assisted intervention (MICCAI)
Zhou SK, Georgescu B, Zhou X, Comaniciu D (2005) Image-based regression using boosting method. In: Proc IEEE intl conf on computer vision (ICCV)
Zhou SK, Zhou J, Comaniciu D (2007) A boosting regression approach to medical anatomy detection. In: Proc IEEE conf computer vision and pattern recognition (CVPR)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Criminisi, A. et al. (2013). Anatomy Detection and Localization in 3D Medical Images. In: Criminisi, A., Shotton, J. (eds) Decision Forests for Computer Vision and Medical Image Analysis. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-4929-3_14
Download citation
DOI: https://doi.org/10.1007/978-1-4471-4929-3_14
Publisher Name: Springer, London
Print ISBN: 978-1-4471-4928-6
Online ISBN: 978-1-4471-4929-3
eBook Packages: Computer ScienceComputer Science (R0)